Connect with random people instantly. Find them in the world’s largest group chat. The “Omegle” for people who don’t want to get creepy messages from old people and weird strangers! Free private chat forever, and meet people along the way. Zonish is also great for you to contact your friends anonymously. is also the best way to contact your friends anonymously, without your parents finding out! Our site is pretty much a way for you to launder your chats. Statistically, the chance of someone finding your chat is impossible, unless they are with you in real life, looking at your computer or device. We hope to make the internet a safer and more secure place for everyone to chat on, without the risks of being spied on, by anyone untrustworthy. Talking to strangers online can be sketchy, so if you are ever talking to someone you don’t feel comfortable with, please just leave the chat. If you are reading this, please let us know if you have any ideas, questions, or concerns for our website here: [email protected] Thanks for reading and enjoy chatting!

Build a virtual insurance assistant to help process claims


This code pattern explains how to create a platform to help insurance agents process claims. We use IBM® Watson™ natural language processing capabilities to understand, classify, and retrieve information to reduce repetitive tasks. In turn, this allows the agent to tackle more creative and complex problems, and most customers receive answers to their questions faster with the help of a Watson-based virtual assistant.


We create the virtual insurance assistant using Node.js and Watson Assistant. The assistant uses Watson Discovery to answer policy questions. For claims processing, the assistant uses Watson Natural Language Understanding to recognize what type of repair is needed when recommending a mechanic.

The mechanic recommendations are built by using Watson Knowledge Studio to create custom entities for mechanic reviews and Watson Natural Language Understanding to process the reviews and to provide the best recommendations based on repair type. A separate tutorial walks you through the steps to build a custom model and deploy it to Watson Natural Language Understanding. By combining our custom entities with built-in recognition of the sentiment (for example, positive or negative) of each review, we are able to rank mechanics by sentiment for each repair type. When the customer describes a claim to the virtual assistant, the deployed model determines what type of repair is needed to narrow down the choice of mechanics.

We made answering policy questions part of our Watson Assistant dialog. In this case, when Watson Assistant detects that your intent is a policy inquiry, it forwards your question to Watson Discovery. To allow Watson Discovery to understand insurance policy documents, follow the separate tutorial, which uses Smart Document Understanding to train Watson Discovery to read the sections of an insurance policy document. Then, the documents are put in a collection for Watson Discovery. Watson Assistant queries Watson Discovery directly and returns the answer to your policy question.

For a fully functional virtual insurance assistant, complete the following tutorials first:

The resulting trained Discovery collection is used for policy inquiries. The deployed model from Watson Knowledge Studio and the Watson Natural Language Understanding service is used to understand claim descriptions.

When you have completed this code pattern, you understand how to:

  • Process complex insurance documents with Watson Discovery to efficiently answer customer policy questions
  • Use Watson Knowledge Studio to create custom models and entities to understand and classify mechanic reviews more accurately
  • Create a web-based application that features a virtual assistant that can answer policy questions and make recommendations based on which mechanics are highly reviewed and covered by the policy.


Virtual insurance agent flow diagram

  1. Insurance policy documents are uploaded to Watson Discovery and then annotated using the Smart Document Understanding tool.
  2. Mechanic review documents are uploaded to Watson Knowledge Studio and then annotated to create custom entities and relationships.
  3. The user chats through a web application to talk to Watson Assistant.
  4. Watson Assistant answers policy questions by using Watson Discovery querying capabilities.
  5. The assistant recommends a mechanic based on the type of damage that is done to the vehicle and on the sentiment of the customer reviews.


Find the detailed steps for this pattern in the readme file. The steps show you how to:

  1. Clone the repository.
  2. Gather the credentials for the mechanic recommender.
  3. Gather the credentials for policy inquiries.
  4. Create the Watson Assistant skill.
  5. Deploy the application.
  6. Use the app.

This code pattern explained how to create a platform to help insurance agents process claims. It’s part of the Build a customer care solution to help your customers manage their insurance claims and get automobile service information.